Interview with Tim, Founder of Creader: Empowering AI to Remember the World and Preserve Stories for Authors

Original Title: "Interview with Creader Founder Tim: Letting AI Remember the World and Leaving the Story to the Author"
Original Author: Watcher Beating

On July 23, Keigo Higashino passed away at the age of 68.

Over the past forty years, he wrote 106 books. "Journey Under the Midnight Sun," "Malice," "The Devotion of Suspect X," "The Miracles of the Namiya General Store," together they constitute a vast parallel world.

Many readers are not unfamiliar with the world within those pages. They know that Kyoichiro Kaga will continue his investigation along the streets of Tokyo, Yukawa Manabu can always see the hidden truth from physical phenomena, and they also know that beyond the cases, there are families in debt, students suppressed by the pressure to excel, and ordinary people unable to escape their past.

The crime is just the entrance. What truly remains in the story is how desires arise, how secrets expand, and how a person is slowly pushed towards the ending by their own choices.

The world depicted by Keigo Higashino appears real because everything has a source. A lie uttered three chapters ago by a person will not simply disappear; a childhood experience will alter the fate of those who walk side by side many years later; a misplaced cup, an unsent letter, may regain significance before the story reaches its conclusion.

Detective fiction condenses the complex world into a scene one can enter. In reality, many things remain unexplained, many relationships end abruptly, but in these hundreds of pages of twists and turns, at least some traces can be traced, some choices will have consequences.

Readers thus find a temporary resting place.

Writers ensure that this parallel world always maintains its gravity. The more complex the worldview, the harder it is to maintain this gravity. Characters accumulate, timelines intersect, a casually written sentence may become a foreshadowing a hundred thousand words later. A character cannot suddenly forget their past, a war cannot happen in the wrong year, a relationship cannot shift direction for no reason.

What is truly lacking in long-form writing is often the memory that encompasses the entire world.

What Creader aims to handle is precisely this part of the work. It extracts characters, places, events, relationships, and timelines from novels, allowing them to become interconnected structures.

Amidst numerous AI products attempting to generate stories for people, Creader's founder Tim is more concerned with another issue: Can technology enter the realm of creation without hastily completing everything for the author?

This is not the first time Tim has approached this question.

In 2014, Tim came to the UK. At that time, his English was not proficient, and web novels became his gateway to another world. Later, he studied computer science, worked on a reading platform, researched blockchain and intellectual property, and also joined a startup focused on IP-based infrastructure. Over more than a decade, technology kept evolving, but the fundamental questions remained unanswered. How can one fully express the world in their mind without losing their own judgment without the help of tools?

By the end of 2025, Tim started to do this again. He believed that the most essential part of writing was still those unaccelerated moments. The author didn't know the answer yet, the characters still had several possibilities, and the story hadn't prematurely turned into something complete, coherent, but no longer belonged to anyone.

The Gravity of the World

Tim loves reading web novels as well as historical novels. He recently read one set during the Xianfeng period. The author placed the characters in the Qing Dynasty, the Anglo-French allied forces, the Battle of Taku Forts, and the changes in the Southeast Asian Chinese community. Real history formed the boundaries, while the fictional characters lived, migrated, and made choices within those boundaries.

Tim liked this style of writing. History was not merely used as a backdrop; it continuously interwove with the characters' destinies. A reader might approach a real war through a fictional character, and due to knowing the war's eventual outcome, worry about the character's yet-unfulfilled fate.

The believability of the world comes from the connection between history, characters, and consequences.

Beat of Perception: How do you judge if a story is a good story?

Tim: What matters most to me is whether the characters truly lived in that world. A story can have a very intricate setting, but if the characters are merely tools to drive the plot forward, readers will quickly notice. The stories that truly stick with me are those where every character has their reasons. Even if they do something wrong, you can understand why they ended up there.

Lately, I've been reading a lot of historical novels and alternate history. Historical novels are fascinating because the author cannot act entirely freely. They must respect what has already happened while creating characters within the gaps left by real history.

For example, I read a novel set during the Xianfeng period, involving the relationship between England, France, and the Qing Dynasty, the Battle of Taku Forts, and also depicted the Chinese in Luzon and Java. At certain points in the story, I pause to look up real history. A fictional tale brings me back to reality.

For me, that is a story coming to life. It doesn't lock you within the novel but launches you from the novel to reevaluate the outside world.

Insightful Beating: You mentioned the novel "Notes of a Crocodile," which won the Booker Prize this year. What attracted you to it?

Tim: It is set in Japanese-occupied Taiwan and follows a Japanese female writer and a Taiwanese translator on a journey that intertwines food, language, colonial relationships, and the emotions between the two individuals. I particularly liked its treatment of "translation." Translation is not just about converting a sentence into another language but about how one person helps another understand a foreign place. There is both knowledge and power dynamics at play. Who is describing this world and who is interpreting for whom will ultimately influence what the reader sees.

This also made me think that literature should not be the sole privilege of professional writers. Anyone who earnestly records their relationship with themselves and the world is already engaged in writing. Ordinary people's experiences are not necessarily lacking in value; most of the time, they just lack a way to organize those experiences.

What technology can truly help with is enabling this part, allowing something that has already been experienced to be expressed more completely.

A Thought Pursued for Over a Decade

In 2014, Tim arrived in the UK. In a foreign language environment, web novels provided him with initial stability. He was drawn to the vast world, clear rules, and evolving character relationships within them. He also began to ponder whether the creation and serialization mechanisms established in Chinese online literature could appear in the English-language market.

To answer this question, he started learning computer science, later joined a major tech company in China, starting from operations. He then pursued postgraduate studies in supercomputing, delving into blockchain and intellectual property. He and his partners participated in competitions, wrote whitepapers, gave presentations, attempting to move the rights and revenue distribution of stories onto the blockchain. Subsequently, he successively joined companies like Story Protocol and FLock, continuing to explore IP, blockchain, AI, and the developer ecosystem.

Although this path seems to have taken a long detour, it ultimately led back to writing.

Insightful Beating: What was the starting point for becoming a Creader?

Tim: Since I was young, I have always enjoyed structured worlds. I played "Pokémon," "Fire Emblem," and "Golden Sun," and I even built Gundams. What attracted me was not just a single character but that these worlds had their own rules. Characters, places, history, and relationships could continually expand, but they were not randomly pieced together.

After arriving in the UK, this feeling became even more pronounced. At that time, my English was not good enough, and web novels were both an escape and a refuge for me. It allowed me to have a familiar world to enter in a foreign environment.

At that time, I was thinking about whether the creation and publishing mechanism of Asian web literature could be established in the Western market. To do this, I started learning technology and even created some very small websites. My undergraduate project was a reading platform, but at that time, both my technical skills and understanding of business were limited, so I didn't truly pursue it further. However, I never forgot about this.

Dongcha Beating: Why did you later shift to blockchain and IP?

Tim: At that time, I believed that the most important issue in the creative industry might be ownership. It has never been transparent enough to know who wrote a story, how it is subsequently adapted, and how revenue is distributed. Blockchain seemed to provide a new infrastructure where works could be registered, rights could be tracked, and income could be automatically distributed according to rules.

This system could be technically established, but the deeper I delved into it, the more I realized that it did not solve the fundamental problem of creation itself. Wallets, tokens, registration processes might actually make reading and writing more cumbersome. We addressed how a work could be rightfully owned after completion but did not answer how a work could transform from a vague idea into a real story before completion.

This is also the reason for the change in direction later on. The issue lies not only in economic relationships but also in the cognitive process of human beings.

Dongcha Beating: Why restart Creader now?

Tim: One very direct reason is that AI programming tools allow individuals to accomplish what previously required a team.

In the past, to create a complex product, one had to consider fundraising, hiring, and development cycles. Now, one person can quickly create a prototype to first validate the most critical parts. This brought me back to the issue ten years ago. However, generative AI also made me see another danger. Many products are accelerating output without truly helping creators think. It can quickly provide you with a complete piece of text, but completeness does not necessarily mean it conveys what you want to express.

I began to realize that what really needs to be protected is not the act of writing but the ability to make judgments during the writing process.

Writing from Memory

Tim refers to Creader as a "narrative engine." It tries to retain the familiar writing path for authors—open the chapter and start writing directly. When help is needed, dialogue, structure, and analysis panels can be accessed; when not needed, these functions recede behind the page.

A novel is divided into several interconnected levels: body text, scene, chapter, character, location, timeline, rules, and relationships. The system continuously reads the content written by the author, incorporating the confirmed information into the internal record of the story.

In a growing world, Creader seeks to maintain what lies beyond the limits of human memory.

Dynamic Insight Beating: Why do you refer to Creader as a "Narrative Engine" instead of an AI Writing Tool?

Tim: Because a writing tool often implies generation: you give it a prompt, and it writes a sentence for you. But narrative is more than just sentences. It involves characters, events, time, relationships, and how the entire world operates. What Creader truly aims to deal with are the connections between these elements.

We primarily look at two types of consistency. The first is narrative consistency. For example, whether a character's transformation has been foreshadowed, whether a subplot has been resolved, or if a chapter genuinely advanced the story. The second is temporal consistency. For instance, what a character knows now, what they don't know, what they did three days ago, and whether the distance between two locations allows them to be at a certain place at a given time.

Over time, many authors of long novels find it challenging to remember the whole world at once. Here, AI is best suited not for making decisions but for memory and reminders.

Dynamic Insight Beating: In practical terms, how does it differ from using Word, Google Docs, or directly chatting with a large model?

Tim: We want the primary pathway always to be writing. Users should be able to start on a blank page without having to complete dozens of character profiles first or learn a complex software system. Other functionalities should be like side quests, appearing when needed.

For example, if you get stuck midway, you can open a panel with a shortcut key to ask what a character did previously or check if this section contradicts earlier setups. After writing, the system can provide annotations similar to an editor.

The issue with general chat tools is that each conversation pushes you into the next round. They easily offer new content continually but struggle to sustain a long-term internal structure of a story.

Creader extracts story facts from the main text. Characters, places, events, and relationships are no longer just names scattered throughout tens of thousands of words but instead enter the same knowledge system. The AI doesn't rely on a temporary chat log; it taps into the internal reality that has already been established within the story.

Dynamic Narrative: Will this in turn make the novel more formulaic?

Tim: This is something we are very cautious about. In the early stages, we chose works such as "Dream of the Red Chamber" and "Hamlet" as model learning materials for narrative analysis, and later expanded to approximately thirty works. The purpose is not to learn the style of a particular author, much less to tell authors how to imitate, but to find some underlying questions that still hold across different works.

For example, whether a descriptive passage serves a narrative function, whether a metaphor comes from genuine character observation, or whether a conflict changes a character's relationship. The system can raise these questions, but it cannot turn literature into a uniform answer.

We are closer to being editors rather than ghostwriters. An editor can say, this part seems to lack motivation, this storyline has not appeared for a long time, or this explanation is too detailed. But the author is entirely free to disagree. There are no grading standards in literature that everyone must follow.

Dynamic Narrative: Will Creader allow AI generation?

Tim: It will allow it, but generation is not the core. Different users need different things. Professional writers may not want AI to enter the main text at all, only needing help in organizing characters, timelines, and foreshadowing. Regular users may have a very rich life experience but may not know how to structure it, and may need more assistance.

The key is to maintain boundaries. We hope that in the future, we can clearly distinguish which content is independently completed by humans, which is AI-assisted editing, and which is mainly generated by AI. Using AI itself does not mean there is no creativity, but readers should know how it was accomplished.

I don't think we have to choose between "purely manual" and "fully generated." The question is whether the author continues to make decisions, retains their intent, experience, and responsibility.

Dynamic Narrative: If a person has their own ideas and creativity, and only entrusts AI with tasks such as typing and organizing materials, is this still considered creation?

Tim: I think this is a very interesting question - how do you define creation?

For example, when you are creating an article, what you truly invest in are your ideas, creativity, and how you want to organize which materials. In the past, these things had to be done bit by bit through handwriting and typing, and part of it, in my opinion, was purely grunt work. Now, by using AI to replace this grunt work, is it still considered creation? I think it is.

First of all, AI should still be defined as a tool. It cannot replace humans. At least for now, most AI generation still needs to be initiated by humans. You have to communicate with it, tell it what you want to write, from what perspective, and what you hope to achieve in the end.

Some people may have a great idea but lack the ability to express it fully. Now, with the help of AI, they have accomplished this without erasing their original idea. They are still creating; they are just using a new tool.

Dynamic Beating: How should the author's identity be determined if the final text is mainly completed by AI?

Tim: I think in the future, we need to differentiate among three scenarios: human creation, AI-assisted creation, and AI-generated creation.

Some people only use AI to check grammar and organize their thoughts, some let AI generate a part of the content, and others may use AI for almost the entire creation. All these approaches can coexist, but there should be clear labels to let readers know how the work was produced.

Previously, there have been cases where writers were exposed for using AI for a significant portion of their work. The real source of anger may not be solely that they used AI, but rather the lack of disclosure, and even treating "undetected by readers" as a kind of success.

Professional writers have their own thinking and creative concepts. The fact that they can collaborate with AI to write a book where readers do not perceive AI's involvement does not mean just anyone can do it. The idea of "If I were in their place, I could do the same" may not always hold.

Dynamic Beating: However, many readers still instinctively reject AI-generated novels.

Tim: If a story is good enough and the language is good enough, I personally would not refuse to read it just because it used AI. But what many people worry about is whether AI is meant to replace authors. The media also often describe AI as "what it can replace," creating a direct sense of threat for creators.

I think it's not a bad thing for some people to stick to traditional methods. Programming is the same; some people prefer to write line by line. AI is not omnipotent; traditional methods still hold value at times.

The key is to understand why someone is using AI.

A professional writer who can write eight thousand or ten thousand words a day may not need AI to generate content for them at all. In contrast, what they may truly need is to organize their thoughts. They might have so many characters, clues, and plots in their mind; how should they incorporate them?

So the role of AI is different for different people. Some need generation, while others only need collaboration. Tools should adapt to human ability rather than require everyone to write in the same way.

Delaying the Answer

The most obvious problem with AI-generated writing is factual errors, clichés, and language repetition. But Tim believes the more insidious danger is speed; AI can always provide an answer too quickly that may appear correct.

The text becomes complete, but the thinking may stop before completion.

Tim refers to this state as "premature coherence." Large models excel at finding the most reasonable completion for a gap, while creativity precisely requires the gap to exist temporarily. Characters can be unstable, motivations can conflict, and an idea can linger nameless for a long time.

In these undecided parts, creators have the opportunity to discover what they really want to write.

Beating It Out: Even when you write something yourself, why do you still prefer to type it out?

Tim: Interacting with AI is rapid. It's a back-and-forth process. It generates a paragraph, you read it, find something off, and immediately start the next round of dialogue. Your brain keeps moving forward, making it challenging to truly slow down.

But it's different when you write yourself. Writing is actually a process of slowing down the speed of thinking in your mind. When you're halfway through, you pause and think, "Am I on the right track now? Am I writing what I really want to write?"

When directly using AI generation, you are more in the mode of reading and judging its answers. If something's wrong here, you let it correct it; if something's not right there, you immediately move to the next round. It lacks the process of slowly forming your own sentences.

So, I believe that whether it's handwriting or typing by yourself, this old-fashioned writing method helps slow down your thinking, giving you more time to constantly question the value of your expression.

Beating It Out: For you, what is the most precious part of writing or literature?

Tim: Of course, I do not come from a literary background; I view literature from a computer background. For me, literature has two main meanings.

The first is to record your interaction with the world. Why do people record and write? Initially, it was hoped that many facts could be seen by future generations. Where a person lives, what they have experienced, how they understand that era can all be preserved in writing.

The second thing is to record the imagination in your mind. When people see more, experience more, and interact more with the world, their imagination will also be opened up. Why do we have science fiction, fantasy, why do we have "One Hundred Years of Solitude"? It's because an imagination sprouted in someone's mind, then was recorded, and finally became a world that does not exist in reality but can be entered by many people.

I think the essence of literature is still to express the inner world of a person.

Everyone is thinking about something, it's just that they may not be willing to speak it out, or willing to post it on Weibo or other public social networks. But sometimes, they still want to record this moment's thoughts, so they write a note.

Literature is not mandatory, it doesn't mean you have to show it to others once you write it.

If you keep this moment's thoughts to yourself, I think it can also be literature. The most important thing is that you have recorded what's in your mind.

Dynamic Insight Beating: I heard that you also want to incorporate Creader into the education scene, how was this considered?

Tim: We are in contact with some institutions in Singapore and Vietnam to see how this product can be used in education.

In our generation, we didn't have AI as kids. Because there was no AI, when we encountered a problem, we had to learn by ourselves and find solutions on our own. This process leaves a background layer for thinking. You know you have to think, to transform, to turn what you see into your knowledge. But for children born after 2005, 2010, AI may accompany them for a long time. At the moment when they most need to learn and establish self-learning ability, they already have a tool that can provide answers anytime.

In the next five to ten years, there may be a kind of inertia where I see something unfamiliar, and my first reaction is to ask AI.

The problem is, the human brain has a very important ability. We can connect what we see in life, what we learn in class, and some unrelated things, and finally form our own understanding. Models are better at providing answers along the lines of relevance. If a person only receives these already organized relevant contents for a long time, their thinking may become more and more reliant on existing paths.

So in the education scene, we actually do not want to provide generation right from the start. Students should first write an outline on their own, think about what to write based on the outline, and then complete the text. Teachers can see how they modify it, how they interact with the system, and how an idea gradually forms.

First, Get the Text Right

Over the next month, Tim plans to work more closely with a Vietnamese art publication.

This will also be the first time the product faces specific regional differences. As a set of writing tools enters another country, not only the interface language changes.

Dynam Beat: What Is Creader's Next Development Plan?

Tim: Next, we may collaborate with an organization that helps Vietnamese artists enter the international market. They publish a magazine annually, distributed in various parts of the world, introducing Vietnamese artists. We hope to see if Creader can enter their actual creative, editing, and publishing processes. It's also a learning experience for us because the feedback cycle of professional writers and organizations is quite long. They are often already writing a book and won't use it today and give you a conclusion tomorrow.

This is a small and exquisite product, and many things still need to be placed in real usage scenarios to know if they are useful.

Dynam Beat: Will Different Authors from Different Countries Using the Same Product Face Challenges?

Tim: Yes. Language is a significant difference.

For example, British English and American English are two very different language habits. The most superficial differences are spelling and word usage, such as colour and color, flat and apartment, lift and elevator. Furthermore, there are differences in slang, conversational style, and writing rhythm.

We have encountered a British author, but he is writing a story set in the United States. When he writes, he needs to constantly check dictionaries, references to confirm if an American character would speak this way because a person's educational background influences their writing. If you have been educated in British English, many words will instinctively be in British expressions. Even for professional authors, writing is not just about putting words on paper and being done. They have to constantly research, check, and replace.

Currently, we mainly support British English, American English, and Chinese. We will also explore the Japanese, Korean, and French markets in the future. The writing atmosphere in Europe is strong, while the United States has many self-published authors, and each market has its unique writing and publishing methods.

Dynam Beat: After the Emergence of AI, Will Future Content Still Be a Book or an Article? Will it Become Something Interactive with Readers?

Tim: We are also considering interactive novels, world-building, and multi-line narratives. But in the end, I still feel that the imaginative space that text provides far exceeds that of video and images. Once you see an image, a relatively fixed image forms in your mind, making it hard to completely detach from it.

However, when reading text, everyone can imagine differently. Why are there so many fanfics and fan art for a work? It's because everyone starts from the same piece of text, yet ends up seeing different things.

Of course, there can be interactive novels in the future, allowing readers to enter different narratives and letting a world sprout many stories. But first and foremost, we still need to do text well.

Dynamic Inquiry: Will investors think this is not a sizable enough business?

Tim: They might. When talking to some investors, they may compare it to directions like Agent and AI memory layers, thinking that a writing tool is not a particularly large business. It can certainly be framed in the context of a "memory layer," saying that we are helping AI store the memory of a world. That narrative works, but I feel it's unnecessary.

I'm building this product to help people tell a good story. If it can help me tell a good story needed for fundraising, that's also a validation. But is it really necessary to hype it up so much? I don't think it's essential.

It may not be a big money-making business, but it can be a sustainable product. Investors who are interested, understand this matter, can discuss it. But I'd rather focus on doing what I love.

This year's goal is also straightforward: to have one hundred authors truly using Creader, with ten of them completing and publishing their own books through it. Achieving this, I believe, would meet this year's KPI.

I believe that as AI-generated content becomes more prevalent, people will also seek out a relatively clean space.

The Time That Gets Cut

In "Time and Free Will," Bergson distinguishes between two types of time. One is the divisible and measurable time, belonging to clocks, calendars, and production schedules: one minute following another, where each unit appears the same.

The other time occurs within human consciousness. The past does not truly disappear but continually enters the present. A moment of hesitation may carry a memory from ten years ago, and the words we write down bear the residual heat of yesterday's argument.

Bergson referred to it as “duration.” And writing takes place in such time.

An author pauses between two words, deletes a paragraph just written, and retrieves it the next day. They may be unable to make a decision about a character or may walk away from the desk halfway through writing. During that time of non-production, something is still changing; it just hasn’t become a sentence yet.

Creation is not about converting time into words. Time itself is the material of creation.

A large model can generate a thousand words in just a few seconds. It can quickly mobilize existing patterns in the language and predict the most likely expression to come based on the context. It pauses, but that is a wait in a computational sense, not a person reinterpreting themselves in hesitation.

Borges compressed vast amounts of time into a very short space, while Proust continuously extends a single moment into the depths of memory. Different languages are not just a set of stylistic choices but also document how a person experiences the world, endures pauses, and interacts with their own time.

The flaws in writing also belong to this time.

An unresolved turn that was not fully tightened, an overly obstinate repetition, a judgment an author may no longer agree with many years later—all indicate that the person who wrote it was once in a specific position. At that time, they only knew these aspects and could only go this far.

Imperfection is sometimes not due to a technical deficiency but because the text is still evidence connected to a finite individual.

Creader is caught in this contradiction, attempting to provide its answer.

Tim described Creader as a piece of land. What a tool can do is not to prematurely grow a forest but to preserve the soil, tidy the boundaries, and allow a still unformed world a space to continue growing.

Land is different from a production line. A production line demands stability, accuracy, and on-time delivery, while land allows waiting. Seeds may be slow to sprout, branches may grow in the wrong direction, and a thicket of weeds can also recreate a new world.

Understanding creation as land means that the tool does not offer a faster way to reach the finish line but a way to accommodate unfinished space.

In an era where conclusions come too easily, we can also choose not to finish the story for the time being.

Original Article Link

Welcome to join the official BlockBeats community:

Telegram Subscription Group: https://t.me/theblockbeats

Telegram Discussion Group: https://t.me/BlockBeats_App

Official Twitter Account: https://twitter.com/BlockBeatsAsia